Triple
T10792992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kim Ju Ae |
E254628
|
entity |
| Predicate | publicOfficeHeld |
P30303
|
FINISHED |
| Object | none known as of 2024 |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: none known as of 2024 | Statement: [Kim Ju Ae, publicOfficeHeld, none known as of 2024]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publicOfficeHeld Context triple: [Kim Ju Ae, publicOfficeHeld, none known as of 2024]
-
A.
heldPoliticalOfficeIn
Indicates that an entity served in a political office or position within a specified governmental body or jurisdiction.
-
B.
hasHeldOfficeType
chosen
Indicates that an entity has at some time occupied or served in a specified type or category of office or position.
-
C.
describesOfficeHeld
Indicates that one entity specifies or characterizes the particular office or position held by another entity.
-
D.
memberHeldOfficeFrom
Indicates that a member began holding a particular office or position starting from a specified date or time.
-
E.
aboutOfficeHeld
Indicates that one entity is related to, or provides information about, a specific office or position that is or was held by another entity.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d732f7ad408190af4727dd9d459498 |
completed | April 9, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69d6f316940c819092a96c429629fdef |
completed | April 9, 2026, 12:30 a.m. |
Created at: April 8, 2026, 9:17 p.m.